Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control

arXiv:2401.01085v2 Announce Type: replace-cross
Abstract: Natural language processing (NLP) has received unprecedented attention. While advancements in NLP models have led to extensive research into their backdoor vulnerabilities, the potential for these advancements to introduce new backdoor threats remains unexplored. This paper proposes Imperio, which harnesses the language understanding capabilities of NLP models to enrich backdoor attacks. Imperio provides a new model control experience. Demonstrated through controlling image classifiers, it empowers the adversary to manipulate the victim model with arbitrary output …

abstract arxiv attacks attention backdoor capabilities control cs.cr cs.lg language language processing language understanding natural natural language natural language processing nlp nlp models paper processing research threats type understanding vulnerabilities